lacvet/AX-Copilot-Codex
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

코드탭 query/history 조립 구조를 단계형 서비스로 분리

Browse Source 
- AgentLoopQueryAssemblyService를 추가해 session learning refresh, queued command/query window 준비, code working set supplemental context 부착을 단계형으로 정리함

- AgentLoopService는 orchestration 중심으로 단순화하고 claw-code의 staged query/history 흐름과 비슷하게 책임을 재배치함

- AgentLoopQueryAssemblyServiceTests를 추가하고 SessionLearningCollectorTests를 영어 기준으로 정리했으며 dotnet build 및 targeted dotnet test(56 통과, 경고/오류 0)로 검증함
This commit is contained in:
lacvet
2026-04-16 02:07:26 +09:00
parent f0f1f76f48
commit 2e1c7be8c3
7 changed files with 255 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@@ -1,5 +1,22 @@
# AX Commander
- Update: 2026-04-16 02:05 (KST)
- Continued the Code-tab context reliability work with a structural refactor that moves query/history assembly closer to the staged shape used by `claw-code`.
- Added `src/AxCopilot/Services/Agent/AgentLoopQueryAssemblyService.cs` so `AgentLoopService` no longer directly owns all of the following responsibilities in one place:
- refreshing session learnings for non-Code tabs
- projecting queued commands into the message list
- preparing the query window
- appending Code working-set supplemental context before request dispatch
- `src/AxCopilot/Services/Agent/AgentLoopService.cs` now delegates staged assembly to `AgentLoopQueryAssemblyService.PrepareHistory(...)` and `PrepareRequest(...)`, leaving the loop focused more narrowly on orchestration, hooks, tool execution, and retry flow.
- Added `src/AxCopilot.Tests/Services/AgentLoopQueryAssemblyServiceTests.cs` to lock:
- non-Code session-learning injection
- Code-tab skip behavior for session learnings
- Code working-set supplemental message injection before the tool reminder
- Rewrote `src/AxCopilot.Tests/Services/SessionLearningCollectorTests.cs` in English-only comments and assertions so the test file itself also follows the new encoding/comment rule.
- Validation:
- `dotnet build src/AxCopilot/AxCopilot.csproj -c Release -v minimal -p:OutputPath=bin\\verify_query_assembly_structure\\ -p:IntermediateOutputPath=obj\\verify_query_assembly_structure\\` warnings 0 / errors 0
- `dotnet test src/AxCopilot.Tests/AxCopilot.Tests.csproj -c Release -v minimal --filter "AgentLoopQueryAssemblyServiceTests|AgentLoopIterationPreparationServiceTests|AgentLoopLlmRequestPreparationServiceTests|AgentMessageInvariantHelperTests|SessionLearningCollectorTests|CodeTaskWorkingSetServiceTests|AgentLoopE2ETests" -p:OutputPath=bin\\verify_query_assembly_structure_tests\\ -p:IntermediateOutputPath=obj\\verify_query_assembly_structure_tests\\` passed 56
- Update: 2026-04-16 01:28 (KST)
- Added an encoding rule to `AGENTS.md`: comments inside code files must be written in English only, and any broken mojibake strings found in touched code files should be rewritten in English before commit.
- Reviewed the recent Code tab runs again. On `2026-04-16`, the request message count still grew during long runs (`messages=7 -> 125`, and another run `118 -> 139`), so the main issue is not raw context length. The problem is context fidelity: build/file evidence is being compacted too aggressively while tool-trace repair noise is repeatedly inserted.